Search Results for author: Jiahai Wang

Found 28 papers, 14 papers with code

Analytical Reasoning of Text

1 code implementation Findings (NAACL) 2022 Wanjun Zhong, Siyuan Wang, Duyu Tang, Zenan Xu, Daya Guo, Yining Chen, Jiahai Wang, Jian Yin, Ming Zhou, Nan Duan

In this paper, we study the challenge of analytical reasoning of text and collect a new dataset consisting of questions from the Law School Admission Test from 1991 to 2016.

Disentangling Reasoning Capabilities from Language Models with Compositional Reasoning Transformers

no code implementations20 Oct 2022 Wanjun Zhong, Tingting Ma, Jiahai Wang, Jian Yin, Tiejun Zhao, Chin-Yew Lin, Nan Duan

This paper presents ReasonFormer, a unified reasoning framework for mirroring the modular and compositional reasoning process of humans in complex decision-making.

Decision Making

Learning Generalizable Models for Vehicle Routing Problems via Knowledge Distillation

1 code implementation14 Oct 2022 Jieyi Bi, Yining Ma, Jiahai Wang, Zhiguang Cao, Jinbiao Chen, Yuan Sun, Yeow Meng Chee

Recent neural methods for vehicle routing problems always train and test the deep models on the same instance distribution (i. e., uniform).

Knowledge Distillation

Improving Task Generalization via Unified Schema Prompt

no code implementations5 Aug 2022 Wanjun Zhong, Yifan Gao, Ning Ding, Zhiyuan Liu, Ming Zhou, Jiahai Wang, Jian Yin, Nan Duan

Task generalization has been a long standing challenge in Natural Language Processing (NLP).

Graph Neural Networks with Dynamic and Static Representations for Social Recommendation

1 code implementation26 Jan 2022 Junfa Lin, Siyuan Chen, Jiahai Wang

GNN-DSR models the short-term dynamic and long-term static interactional representations of the user's interest and the item's attraction, respectively.

Recommendation Systems

Reasoning over Hybrid Chain for Table-and-Text Open Domain QA

no code implementations15 Jan 2022 Wanjun Zhong, JunJie Huang, Qian Liu, Ming Zhou, Jiahai Wang, Jian Yin, Nan Duan

CARP utilizes hybrid chain to model the explicit intermediate reasoning process across table and text for question answering.

Open-Domain Question Answering

Topic-to-Essay Generation with Comprehensive Knowledge Enhancement

no code implementations29 Jun 2021 Zhiyue Liu, Jiahai Wang, Zhenghong Li

For internal knowledge enhancement, both topics and related essays are fed to a teacher network as source information.

Text Generation

Meta-Learning-Based Deep Reinforcement Learning for Multiobjective Optimization Problems

1 code implementation6 May 2021 Zizhen Zhang, Zhiyuan Wu, Hang Zhang, Jiahai Wang

When these problems are extended to multiobjective ones, it becomes difficult for the existing DRL approaches to flexibly and efficiently deal with multiple subproblems determined by weight decomposition of objectives.

Combinatorial Optimization Meta-Learning +3

AR-LSAT: Investigating Analytical Reasoning of Text

1 code implementation14 Apr 2021 Wanjun Zhong, Siyuan Wang, Duyu Tang, Zenan Xu, Daya Guo, Jiahai Wang, Jian Yin, Ming Zhou, Nan Duan

Analytical reasoning is an essential and challenging task that requires a system to analyze a scenario involving a set of particular circumstances and perform reasoning over it to make conclusions.

Neural Relational Inference with Efficient Message Passing Mechanisms

1 code implementation23 Jan 2021 Siyuan Chen, Jiahai Wang, Guoqing Li

Additionally, the structural prior knowledge, symmetry as a special case, is introduced for better relation prediction in more complex systems.

Multi-choice Relational Reasoning for Machine Reading Comprehension

no code implementations COLING 2020 Wuya Chen, Xiaojun Quan, Chunyu Kit, Zhengcheng Min, Jiahai Wang

We propose a multi-choice relational reasoning (McR$^2$) model with an aim to enable relational reasoning on candidates based on fusion representations of document, query and candidates.

Machine Reading Comprehension Relational Reasoning

Neural Deepfake Detection with Factual Structure of Text

1 code implementation EMNLP 2020 Wanjun Zhong, Duyu Tang, Zenan Xu, Ruize Wang, Nan Duan, Ming Zhou, Jiahai Wang, Jian Yin

To address this, we propose a graph-based model that utilizes the factual structure of a document for deepfake detection of text.

DeepFake Detection Face Swapping

A Novel Framework with Information Fusion and Neighborhood Enhancement for User Identity Linkage

1 code implementation16 Mar 2020 Siyuan Chen, Jiahai Wang, Xin Du, Yanqing Hu

The information fusion component adopts a group of encoders and decoders to fuse heterogeneous information and generate discriminative node embeddings for preliminary matching.

A Deep Reinforcement Learning Algorithm Using Dynamic Attention Model for Vehicle Routing Problems

3 code implementations9 Feb 2020 Bo Peng, Jiahai Wang, Zizhen Zhang

However, the fact is, the state of an instance is changed according to the decision that the model made at different construction steps, and the node features should be updated correspondingly.

Combinatorial Optimization reinforcement-learning +1

CatGAN: Category-aware Generative Adversarial Networks with Hierarchical Evolutionary Learning for Category Text Generation

1 code implementation15 Nov 2019 Zhiyue Liu, Jiahai Wang, Zhiwei Liang

This paper proposes a category-aware GAN (CatGAN) which consists of an efficient category-aware model for category text generation and a hierarchical evolutionary learning algorithm for training our model.

Text Generation

Reasoning Over Semantic-Level Graph for Fact Checking

no code implementations ACL 2020 Wanjun Zhong, Jingjing Xu, Duyu Tang, Zenan Xu, Nan Duan, Ming Zhou, Jiahai Wang, Jian Yin

We evaluate our system on FEVER, a benchmark dataset for fact checking, and find that rich structural information is helpful and both our graph-based mechanisms improve the accuracy.

Claim Verification Fact Checking +4

Collective Mobile Sequential Recommendation: A Recommender System for Multiple Taxicabs

no code implementations22 Jun 2019 Tongwen Wu, Zizhen Zhang, Yanzhi Li, Jiahai Wang

Mobile sequential recommendation was originally designed to find a promising route for a single taxicab.

Sequential Recommendation

Improving Question Answering by Commonsense-Based Pre-Training

no code implementations5 Sep 2018 Wanjun Zhong, Duyu Tang, Nan Duan, Ming Zhou, Jiahai Wang, Jian Yin

Although neural network approaches achieve remarkable success on a variety of NLP tasks, many of them struggle to answer questions that require commonsense knowledge.

Question Answering

adaptive direction information in differential evolution for numerical optimization

no code implementations2 Feb 2016 Yiqiao Cai, Jiahai Wang, Yonghong Chen, Tian Wang, Hui Tian, Wei Luo

In most of the DE algorithms, the neighborhood and direction information are not fully and simultaneously exploited to guide the search.

Cannot find the paper you are looking for? You can Submit a new open access paper.